Shuo Lei | Virginia Tech

About Me

I am a research scientist at Sony Research. I received my Ph.D. in Computer Science at Virginia Tech under the supervision of Prof. Chang-Tien Lu. I received an M.Sc. degree and a B.A. degree in Software Engineering at Beihang University. My research interests are in the broad area of machine learning with a particular focus on learning with limited labeled data, including few-/zero-shot learning, self-learning with uncertainty analysis, and applications in computer vision and natural language processing tasks such as semantic segmentation and text classification.

Research Interests

Computer Vision: few-/zero-shot classification, semantic segmentation
Natural Language Processing: multilingual
Machine Learning: meta-learning, robust model learning

News

[May 2023] One paper was accepted by ACL 2023.
[Jul. 2022] One paper was accepted by ECCV 2022.
[Jun. 2022] One paper was accepted by Neurocomputing.
[May. 2022] One paper was accepted by NAACL 2022.
[Aug. 2021] One paper was accepted by ICCVW 2021.
[Jul. 2021] One paper was accepted by TKDD.
[Mar. 2021] One paper was accepted by ICME 2021.

Publications

[ACL’23] TART: Improved Few-shot Text Classification Using Task-Adaptive Reference Transformation
Shuo Lei, Xuchao Zhang, Jianfeng He, Fanglan Chen and Chang-Tien Lu.
The 61st Annual Meeting of the Association for Computational Linguistics(ACL), Toronto, Canada, July 9-14, 2023 (Accepted)
[ECCV’22] Cross-Domain Few-Shot Semantic Segmentation
Shuo Lei, Xuchao Zhang, Jianfeng He, Fanglan Chen, Bowen Du and Chang-Tien Lu
European Conference on Computer Vision 2022 (ECCV), Tel-Aviv, Israel, Oct. 23-27, 2022. [paper] [code]
[NAACL’22] Uncertainty-Aware Cross-Lingual Transfer with Pseudo Partial Labels
Shuo Lei, Xuchao Zhang, Jianfeng He, Fanglan Chen and Chang-Tien Lu
Annual Conference of the North American Chapter of the Association for Computational Linguistics (Findings of NAACL’22), Seattle, Washington, USA, July 2022.[paper] [code]
[Neurocomputing’22] Semantic Inpainting on Segmentation Map via Multi-Expansion Loss
Jianfeng He, Xuchao Zhang, Shuo Lei, Shuhui Wang, Chang-Tien Lu and Bei Xiao
Neurocomputing, Elsevier, 2022
[TKDD] Online and Distributed Robust Regressions with Extremely Noisy Labels
Shuo Lei, Xuchao Zhang, Liang Zhao, Arnold P. Boedihardjo, Chang-Tien Lu
ACM Transactions on Knowledge Discovery from Data (TKDD), 2021. [paper]
[ICME’21] Few-Shot Semantic Segmenation via Prototype Augmentation with Image-level Annotations
Shuo Lei, Xuchao Zhang, Jianfeng He, Fanglan Chen, Bowen Du and Chang-Tien Lu
IEEE International Conference on Multimedia and Expo (ICME), Virtual, Shenzhen, July 5–9, 2021 [paper]
[ICCVW’21] Reducing Noise Pixels and Metric Bias in Semantic Inpainting on Segmentation Map
Jianfeng He, Bei Xiao, Xuchao Zhang, Shuo Lei, Shuhui Wang, Chang-Tien Lu
IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) 2021. [paper]
[EMNLP’20] Towards More Accurate Uncertainty Estimation In Text Classification
Jianfeng He, Xuchao Zhang, Shuo Lei, Zhiqian Chen, Fanglan Chen, Abdulaziz Alhamadani, Bei Xiao and ChangTien Lu
2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Nov. 16-20, 2020. [paper] [code]
[SIGSPATIAL’20] Graph Convolutional Networks with Kalman Filtering for Traffic Prediction
Fanglan Chen, Zhiqian Chen, Subhodip Biswas, Shuo Lei, Naren Ramakrishnan, Chang-Tien Lu
ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (SIGSPATIAL) 2020. [paper] [code]
[TKDD] Robust Regression via Heuristic Corruption Thresholding and Its Adaptive Estimation Variation
Xuchao Zhang, Shuo Lei, Liang Zhao, Arnold Boedihardjo, Chang-Tien Lu
ACM Transactions on Knowledge Discovery from Data (TKDD), 2019. [paper]
[ICDM’18] Robust Regression via Online Feature Selection under Adversarial Data Corruption
Xuchao Zhang, Shuo Lei, Liang Zhao, Arnold Boedihardjo, Chang-Tien Lu
Proceedings of the IEEE International Conference on Data Mining (ICDM), Singapore, Nov. 17-20, 2018. [paper]